mirror of
https://github.com/lancedb/lancedb.git
synced 2025-12-22 21:09:58 +00:00
feat(index): add IVF_RQ index type (#2687)
this expose IVF_RQ (RabitQ quantization) index type to lancedb --------- Signed-off-by: BubbleCal <bubble-cal@outlook.com>
This commit is contained in:
@@ -194,6 +194,37 @@ currently is also a memory intensive operation.
|
||||
|
||||
***
|
||||
|
||||
### ivfRq()
|
||||
|
||||
```ts
|
||||
static ivfRq(options?): Index
|
||||
```
|
||||
|
||||
Create an IvfRq index
|
||||
|
||||
IVF-RQ (RabitQ Quantization) compresses vectors using RabitQ quantization
|
||||
and organizes them into IVF partitions.
|
||||
|
||||
The compression scheme is called RabitQ quantization. Each dimension is quantized into a small number of bits.
|
||||
The parameters `num_bits` and `num_partitions` control this process, providing a tradeoff
|
||||
between index size (and thus search speed) and index accuracy.
|
||||
|
||||
The partitioning process is called IVF and the `num_partitions` parameter controls how
|
||||
many groups to create.
|
||||
|
||||
Note that training an IVF RQ index on a large dataset is a slow operation and
|
||||
currently is also a memory intensive operation.
|
||||
|
||||
#### Parameters
|
||||
|
||||
* **options?**: `Partial`<[`IvfRqOptions`](../interfaces/IvfRqOptions.md)>
|
||||
|
||||
#### Returns
|
||||
|
||||
[`Index`](Index.md)
|
||||
|
||||
***
|
||||
|
||||
### labelList()
|
||||
|
||||
```ts
|
||||
|
||||
@@ -68,6 +68,7 @@
|
||||
- [IndexStatistics](interfaces/IndexStatistics.md)
|
||||
- [IvfFlatOptions](interfaces/IvfFlatOptions.md)
|
||||
- [IvfPqOptions](interfaces/IvfPqOptions.md)
|
||||
- [IvfRqOptions](interfaces/IvfRqOptions.md)
|
||||
- [MergeResult](interfaces/MergeResult.md)
|
||||
- [OpenTableOptions](interfaces/OpenTableOptions.md)
|
||||
- [OptimizeOptions](interfaces/OptimizeOptions.md)
|
||||
|
||||
Reference in New Issue
Block a user